MultiFlow: A unified deep learning framework for multi-vessel classification, segmentation and clustering of phase-contrast MRI validated on a multi-site single ventricle patient cohort
This work addresses automated analysis of cardiac MRI for single-ventricle patients, offering incremental improvements in segmentation and clustering for clinical phenotyping.
The authors tackled automated segmentation and flow phenotyping in single-ventricle patients using a deep learning framework, achieving a Dice score of 0.91 for segmentation and identifying flow phenotypes significantly associated with clinical risks like death or transplantation.
We present a deep learning framework with two models for automated segmentation and large-scale flow phenotyping in a registry of single-ventricle patients. MultiFlowSeg simultaneously classifies and segments five key vessels, left and right pulmonary arteries, aorta, superior vena cava, and inferior vena cava, from velocity encoded phase-contrast magnetic resonance (PCMR) data. Trained on 260 CMR exams (5 PCMR scans per exam), it achieved an average Dice score of 0.91 on 50 unseen test cases. The method was then integrated into an automated pipeline where it processed over 5,500 registry exams without human assistance, in exams with all 5 vessels it achieved 98% classification and 90% segmentation accuracy. Flow curves from successful segmentations were used to train MultiFlowDTC, which applied deep temporal clustering to identify distinct flow phenotypes. Survival analysis revealed distinct phenotypes were significantly associated with increased risk of death/transplantation and liver disease, demonstrating the potential of the framework.